© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90655
    Prev
    Next
    INDEX
    Explanations

    language translation and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voisin
    0.45
    os
    0.44
     voisines
    0.44
    is
    0.44
     maddenin
    0.44
    your
    0.43
    a
    0.43
    la
    0.42
    ారి
    0.42
    :])
    0.41
    POSITIVE LOGITS
    价比
    0.46
    屉
    0.45
    </h4>
    0.44
     丶
    0.44
     Kø
    0.44
    خصوص
    0.43
    čil
    0.43
    managerpage
    0.42
    ̙
    0.42
    Dü
    0.41
    Activations Density 0.007%

    No Known Activations